{"id":"https://openalex.org/W6929304742","doi":"https://doi.org/10.48550/arxiv.2507.10283","title":"FTCFormer: Fuzzy Token Clustering Transformer for Image Classification","display_name":"FTCFormer: Fuzzy Token Clustering Transformer for Image Classification","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W6929304742","doi":"https://doi.org/10.48550/arxiv.2507.10283"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2507.10283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2507.10283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bao, Muyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bao, Muyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zeng, Changyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Changyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yifan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Zhengni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhengni","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Zimu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zimu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng, Guangliang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Guangliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qi, Jun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.13359999656677246,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10235","display_name":"Health disparities and outcomes","score":0.13359999656677246,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.10620000213384628,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10804","display_name":"Health Systems, Economic Evaluations, Quality of Life","score":0.09369999915361404,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6524999737739563},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5916000008583069},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5329999923706055},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4893999993801117},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.40070000290870667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37470000982284546},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.3718000054359436},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3637999892234802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6524999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6380000114440918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5329999923706055},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.25049999356269836},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2507.10283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2507.10283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"deep":[1],"neural":[2],"networks":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"across":[8,144],"various":[9],"computer":[10],"vision":[11,31,67],"tasks,":[12],"largely":[13],"attributed":[14],"to":[15,64,82,88],"their":[16,95],"long-range":[17],"self-attention":[18],"mechanism":[19,117],"and":[20,86,106,130,182],"scalability.":[21],"However,":[22],"most":[23],"transformer":[24],"architectures":[25],"embed":[26],"images":[27],"into":[28],"uniform,":[29],"grid-based":[30],"tokens,":[32],"neglecting":[33],"the":[34,71,148,159],"underlying":[35],"semantic":[36,72],"meanings":[37,73],"of":[38,75,94,150,164],"image":[39,153,175],"regions,":[40,92],"resulting":[41],"in":[42],"suboptimal":[43],"feature":[44,104],"representations.":[45],"To":[46,101],"address":[47],"this":[48],"issue,":[49],"we":[50,108],"propose":[51,109],"Fuzzy":[52],"Token":[53],"Clustering":[54],"Transformer":[55],"(FTCFormer),":[56],"which":[57],"incorporates":[58],"a":[59,110,122,131],"novel":[60],"clustering-based":[61],"downsampling":[62],"module":[63],"dynamically":[65],"generate":[66],"tokens":[68,81],"based":[69],"on":[70,141,152,167,172,178,184],"instead":[74],"spatial":[76,96],"positions.":[77],"It":[78],"allocates":[79],"fewer":[80],"less":[83],"informative":[84],"regions":[85],"more":[87],"represent":[89],"semantically":[90],"important":[91],"regardless":[93],"adjacency":[97],"or":[98],"shape":[99],"irregularity.":[100],"further":[102],"enhance":[103],"extraction":[105],"representation,":[107],"Density":[111],"Peak":[112],"Clustering-Fuzzy":[113],"K-Nearest":[114],"Neighbor":[115],"(DPC-FKNN)":[116],"for":[118,127,136],"clustering":[119],"center":[120],"determination,":[121],"Spatial":[123],"Connectivity":[124],"Score":[125],"(SCS)":[126],"token":[128,137],"assignment,":[129],"channel-wise":[132],"merging":[133],"(Cmerge)":[134],"strategy":[135],"merging.":[138],"Extensive":[139],"experiments":[140],"32":[142],"datasets":[143,181],"diverse":[145],"domains":[146],"validate":[147],"effectiveness":[149],"FTCFormer":[151],"classification,":[154],"showing":[155],"consistent":[156],"improvements":[157],"over":[158],"TCFormer":[160],"baseline,":[161],"achieving":[162],"gains":[163],"improving":[165],"1.43%":[166],"five":[168],"fine-grained":[169],"datasets,":[170,176],"1.09%":[171],"six":[173],"natural":[174],"0.97%":[177],"three":[179],"medical":[180],"0.55%":[183],"four":[185],"remote":[186],"sensing":[187],"datasets.":[188],"The":[189],"code":[190],"is":[191],"available":[192],"at:":[193],"https://github.com/BaoBao0926/FTCFormer/tree/main.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}